SPTS v2: Single-Point Scene Text Spotting
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 15665-15679
DOI: 10.1109/tpami.2023.3312285 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Yuliang Liu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Zhuhai Industry Core and Key Technology Research Project.
Abstract (Originalsprache)
End-to-end scene text spotting has made significant progress due to its intrinsic synergy between text detection and recognition. Previous methods commonly regard manual annotations such as horizontal rectangles, rotated rectangles, quadrangles, and polygons as a prerequisite, which are much more expensive than using single-point. Our new framework, SPTS v2, allows us to train high-performing text-spotting models using a single-point annotation. SPTS v2 reserves the advantage of the auto-regressive Transformer with an Instance Assignment Decoder (IAD) through sequentially predicting the center points of all text instances inside the same predicting sequence, while with a Parallel Recognition Decoder (PRD) for text recognition in parallel, which significantly reduces the requirement of the length of the sequence. These two decoders share the same parameters and are interactively connected with a simple but effective information transmission process to pass the gradient and information. Comprehensive experiments on various existing benchmark datasets demonstrate the SPTS v2 can outperform previous state-of-the-art single-point text spotters with fewer parameters while achieving 19× faster inference speed. Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations. Such an attempt provides a significant opportunity for scene text spotting applications beyond the realms of existing paradigms.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Zhuhai Industry Core and Key Technology Research Project
Zitieren
APA
Liu, Y., Zhang, J., Peng, D., Huang, M., Wang, X., Tang, J., Huang, C., Lin, D., Shen, C., Bai, X., & Jin, L. (2023). SPTS v2: Single-Point Scene Text Spotting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 15665-15679. https://doi.org/10.1109/tpami.2023.3312285
Vancouver
Liu Y, Zhang J, Peng D, Huang M, Wang X, Tang J, et al. SPTS v2: Single-Point Scene Text Spotting. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):15665-15679. doi:10.1109/tpami.2023.3312285
BibTeX
@article{Liu2023,
author = {Liu, Yuliang and Zhang, Jiaxin and Peng, Dezhi and Huang, Mingxin and Wang, Xinyu and Tang, Jingqun and Huang, Can and Lin, Dahua and Shen, Chunhua and Bai, Xiang and Jin, Lianwen},
title = {SPTS v2: Single-Point Scene Text Spotting},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {12},
pages = {15665--15679},
doi = {10.1109/tpami.2023.3312285}
}
EUVIMED