TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.06.2025 · 21 (6) · 1-21
DOI: 10.1145/3734872 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 08.07.2025. Verfasst von Jiahao Lyu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Laboratory of Ethnic Language Intelligent Analysis, Security Governance of MOE, Minzu University of China, Beijing, China.
Abstract (Originalsprache)
Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus spotting pipeline of human beings and impressive performances of Pre-trained Language Models (PLMs) on visual tasks, we ask: (1) “Can machines spot texts without precise detection just like human beings?”, and if yes, (2) “Is text block another alternative for scene text spotting other than word or character?” To this end, our proposed scene text spotter leverages advanced PLMs to enhance performance without fine-grained detection. Specifically, we first use a simple detector for block-level text detection to obtain rough positional information. Then, we fine-tune a PLM using a large-scale OCR dataset to achieve accurate recognition. Benefiting from the comprehensive language knowledge gained during the pre-training phase, the PLM-based recognition module effectively handles complex scenarios, including multi-line, reversed, occluded, and incomplete-detection texts. Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks. Additionally, we attempt to spot texts directly from an entire scene image to demonstrate the potential of PLMs, even Large Language Models (LLMs).
Förderung
- National Natural Science Foundation of China
- Key Laboratory of Ethnic Language Intelligent Analysis
- Security Governance of MOE, Minzu University of China, Beijing, China
Zitieren
APA
Lyu, J., Wei, J., Zeng, G., Li, Z., Xie, E., Wang, W., Ma, C., & Zhou, Y. (2025). TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(6), 1-21. https://doi.org/10.1145/3734872
Vancouver
Lyu J, Wei J, Zeng G, Li Z, Xie E, Wang W, et al. TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(6):1-21. doi:10.1145/3734872
BibTeX
@article{Lyu2025,
author = {Lyu, Jiahao and Wei, Jin and Zeng, Gangyan and Li, Zeng and Xie, Enze and Wang, Wei and Ma, Can and Zhou, Yu},
title = {TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {6},
pages = {1--21},
doi = {10.1145/3734872}
}
EUVIMED