In this report, we present the final results of the ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition. The RoadText challenge is based on the …
We introduce the structured scene-text spotting task, which requires a scene-text OCR system to spot text in the wild according to a query regular expression. Contrary to generic …
A Das, S Biswas, A Banerjee, J Lladós… - Proceedings of the …, 2024 - openaccess.thecvf.com
The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art …
This six-volume set of LNCS 14187, 14188, 14189, 14190, 14191 and 14192 constitutes the refereed proceedings of the 17th International Conference on Document Analysis and …
Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while …
Detecçao de texto em cena tem recebido grande importância nos últimos anos. Os desafios desta tarefa consistem em conceber detectores capazes de lidar com uma ampla gama de …