# Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning

arXiv: https://arxiv.org/abs/1909.07808 · HTML: https://mlsanity.com/paper/1909.07808/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System](https://mlsanity.com/paper/2206.03001/) (2022)
- [Detect Anything via Next Point Prediction](https://mlsanity.com/paper/2510.12798/) (2025)
- [What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels](https://mlsanity.com/paper/2103.04400/) (2021)
- [Revisiting Scene Text Recognition: A Data Perspective](https://mlsanity.com/paper/2307.08723/) (2023)
- [ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting](https://mlsanity.com/paper/2211.10578/) (2022)
- [PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System](https://mlsanity.com/paper/2109.03144/) (2021)
- [Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting](https://mlsanity.com/paper/2203.03911/) (2022)
- [Exploring Better Text Image Translation with Multimodal Codebook](https://mlsanity.com/paper/2305.17415/) (2023)
- [SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization](https://mlsanity.com/paper/2203.10492/) (2022)
- [CLIPTER: Looking at the Bigger Picture in Scene Text Recognition](https://mlsanity.com/paper/2301.07464/) (2023)
- [Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition](https://mlsanity.com/paper/2209.00641/) (2022)
- [OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding](https://mlsanity.com/paper/2407.04923/) (2024)
- [ICDAR 2023 Video Text Reading Competition for Dense and Small Text](https://mlsanity.com/paper/2304.04376/) (2023)
- [An Empirical Study of Scaling Law for OCR](https://mlsanity.com/paper/2401.00028/) (2023)
- [A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges](https://mlsanity.com/paper/2405.12669/) (2024)
- [TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance](https://mlsanity.com/paper/2111.08314/) (2021)
- [RusTitW: Russian Language Text Dataset for Visual Text in-the-Wild Recognition](https://mlsanity.com/paper/2303.16531/) (2023)
- [SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting](https://mlsanity.com/paper/2504.09966/) (2025)
- [IndicSTR12: A Dataset for Indic Scene Text Recognition](https://mlsanity.com/paper/2403.08007/) (2024)

## Abstract (arXiv)

Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data. To address this issue, we introduce a new large-scale text reading benchmark dataset named Chinese Street View Text (C-SVT) with 430,000 street view images, which is at least 14 times as large as the existing Chinese text reading benchmarks. To recognize Chinese text in the wild while keeping large-scale datasets labeling cost-effective, we propose to annotate one part of the CSVT dataset (30,000 images) in locations and text labels as full annotations and add 400,000 more images, where only the corresponding text-of-interest in the regions is given as weak annotations. To exploit the rich information from the weakly annotated data, we design a text reading network in a partially supervised learning framework, which enables to localize and recognize text, learn from fully and weakly annotated data simultaneously. To localize the best matched text proposals from weakly labeled images, we propose an online proposal matching module incorporated in the whole model, spotting the keyword regions by sharing parameters for end-to-end training. Compared with fully supervised training algorithms, this model can improve the end-to-end recognition performance remarkably by 4.03% in F-score at the same labeling cost. The proposed model can also achieve state-of-the-art results on the ICDAR 2017-RCTW dataset, which demonstrates the effectiveness of the proposed partially supervised learning framework.