Dec 15, 2021 · We propose an end-to-end scene text spotting method that tackles scene text spotting as a sequence prediction task. Given an image as input, we ...

The SPTS tackles scene text spotting as an end-to-end sequence prediction task and requires only extremely low-cost single-point annotations.

We propose an end-to-end scene text spotting method that tackles scene text spotting as a sequence prediction task. Given an image as input, we formulate the ...

Jan 4, 2023 · Our new framework, SPTS v2, allows us to train high-performing text-spotting models using a single-point annotation.

The SPTSv2 which achieves 19× faster inference speed tackles scene text spotting as an end-to-end sequence prediction task and requires only extremely low-cost ...

We have proposed SPTS v2, a new scene text spotting paradigm that shows an extremely low-cost single-point annotation can be successfully used to train a ...

End-to-end scene text spotting has made significant progress due to its intrinsic synergy between text detection and recognition.

This work demonstrates that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance, ...

The SPTS v2 can outperform previous state-of-the-art single-point text spotters with fewer parameters while achieving 19× faster inference speed and ...

Our new framework, SPTS v2, allows us to train high-performing text-spotting models using a single-point annotation.