# You Only Recognize Once: Towards Fast Video Text Spotting

arXiv: https://arxiv.org/abs/1903.03299 · HTML: https://mlsanity.com/paper/1903.03299/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2019.

## Built on by (most cited first, 21 of 21)

- [A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer](https://mlsanity.com/paper/2112.04888/) (2021)
- [End-to-End Video Text Spotting with Transformer](https://mlsanity.com/paper/2203.10539/) (2022)
- [MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios](https://mlsanity.com/paper/2505.21333/) (2025)
- [STRIVE: Scene Text Replacement In Videos](https://mlsanity.com/paper/2109.02762/) (2021)
- [Scalable Mask Annotation for Video Text Spotting](https://mlsanity.com/paper/2305.01443/) (2023)
- [GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching](https://mlsanity.com/paper/2401.07080/) (2024)
- [Video Text Tracking With a Spatio-Temporal Complementary Model](https://mlsanity.com/paper/2111.04987/) (2021)
- [FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation](https://mlsanity.com/paper/2305.03327/) (2023)
- [ICDAR 2023 Video Text Reading Competition for Dense and Small Text](https://mlsanity.com/paper/2304.04376/) (2023)
- [Real-time End-to-End Video Text Spotter with Contrastive Representation Learning](https://mlsanity.com/paper/2207.08417/) (2022)
- [DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text](https://mlsanity.com/paper/2312.01938/) (2023)
- [GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking](https://mlsanity.com/paper/2505.22228/) (2025)
- [Contrastive Learning of Semantic and Visual Representations for Text Tracking](https://mlsanity.com/paper/2112.14976/) (2021)
- [ICDAR 2021 Competition on Scene Video Text Spotting](https://mlsanity.com/paper/2107.11919/) (2021)
- [E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles](https://mlsanity.com/paper/2206.02281/) (2022)
- [DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding](https://mlsanity.com/paper/2207.06695/) (2022)
- [Tracking Based Semi-Automatic Annotation for Scene Text Videos](https://mlsanity.com/paper/2103.15488/) (2021)
- [GloTSFormer: Global Video Text Spotting Transformer](https://mlsanity.com/paper/2401.03694/) (2024)
- [VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization](https://mlsanity.com/paper/2404.19652/) (2024)
- [LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model](https://mlsanity.com/paper/2405.19194/) (2024)
- [A Large-scale Dataset for Robust Complex Anime Scene Text Detection](https://mlsanity.com/paper/2510.07951/) (2025)

## Abstract (arXiv)

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.