Scene text recognition with permuted autoregressive sequence models

D Bautista, R Atienza - European conference on computer vision, 2022 - Springer
Context-aware STR methods typically use internal autoregressive (AR) language models
(LM). Inherent limitations of AR models motivated two-stage methods which employ an …

Trocr: Transformer-based optical character recognition with pre-trained models

M Li, T Lv, J Chen, L Cui, Y Lu, D Florencio… - Proceedings of the …, 2023 - ojs.aaai.org
Text recognition is a long-standing research problem for document digitalization. Existing
approaches are usually built based on CNN for image understanding and RNN for char …

Revisiting scene text recognition: A data perspective

Q Jiang, J Wang, D Peng, C Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective.
We begin by revisiting the six commonly used benchmarks in STR and observe a trend of …

Vision transformer for fast and efficient scene text recognition

R Atienza - International conference on document analysis and …, 2021 - Springer
Scene text recognition (STR) enables computers to read text in natural scenes such as
object labels, road signs and instructions. STR helps machines perform informed decisions …