CentripetalText: An Efficient Text Instance Representation f…

Established


22
Citations
47
Refs
2021
Year
Search Works
Work Details
  • DOI 10.48550/arxiv.2107.05945
  • OpenAlex ID W3208795278
  • Type Preprint
  • Language EN
  • Published 13 Jul 2021
  • Source arXiv (Cornell University)
  • Publisher Cornell University
  • Countries 1
  • Institutions 1
  • Added 08 Nov 2021
  • Updated 16 Oct 2026
MENU
0

CentripetalText: An Efficient Text Instance Representation for Scene Text Detection

Preprint 2021 EN Green

Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the hardest problems in this task is how to represent text instances of arbitrary shapes. Although many methods have been proposed to model irregular texts in a flexible manner, most of them lose simplicity and robustness. Their complicated post-processings and the regres…

22

Citations

47

References

3

Authors

0.00

FWCI

Citations by Year
Last 4 years
Topics
Keywords
Authors & Affiliations
3 authors
#AuthorInstitutionsORCID
1 Tao Sheng —
2 Jie Chen —
3 Zhouhui Lian Peking University (CN)

Data: OpenAlex