You Only Recognize Once: Towards Fast Video Text Spotting

TL;DR

This paper introduces a fast, robust video text spotting framework that recognizes text only once per video, significantly reducing computational costs and improving accuracy over traditional multi-stage methods.

Contribution

The authors propose a novel end-to-end trainable text recommender that selects high-quality text for recognition, streamlining the process and enhancing speed and robustness.

Findings

Speeds up recognition by 71 times compared to frame-wise methods

Achieves state-of-the-art accuracy on public benchmarks

Introduces a new large-scale video text dataset (LSVTD)

Abstract

Video text spotting is still an important research topic due to its various real-applications. Previous approaches usually fall into the four-staged pipeline: text detection in individual images, framewisely recognizing localized text regions, tracking text streams and generating final results with complicated post-processing skills, which might suffer from the huge computational cost as well as the interferences of low-quality text. In this paper, we propose a fast and robust video text spotting framework by only recognizing the localized text one-time instead of frame-wisely recognition. Specifically, we first obtain text regions in videos with a well-designed spatial-temporal detector. Then we concentrate on developing a novel text recommender for selecting the highest-quality text from text streams and only recognizing the selected ones. Here, the recommender assembles text tracking, quality scoring and recognition into an end-to-end trainable module, which not only avoids the interferences from low-quality text but also dramatically speeds up the video text spotting process. In addition, we collect a larger scale video text dataset (LSVTD) for promoting the video text spotting community, which contains 100 text videos from 22 different real-life scenarios. Extensive experiments on two public benchmarks show that our method greatly speeds up the recognition process averagely by 71 times compared with the frame-wise manner, and also achieves the remarkable state-of-the-art.