GDText-VM: an arbitrary-shaped scene text detector based on globally deformable VMamba

Abstract Detecting arbitrary-shaped text in natural scenes remains a significant challenge in deep learning research. Contemporary text detectors based on Convolutional Neural Networks face challenges in effectively modeling long-range dependencies. While Vision Transformers theoretically enable glo...

Full description

Bibliographic Details

Published in:	Complex & Intelligent Systems
Main Authors:	Yingnan Zhao, Zheng Hu, Fangqi Ding, Jielin Jiang, Xiaolong Xu
Format:	Article
Language:	English
Published:	Springer 2025-06-01
Subjects:	Computer vision Globally Deformable VMamba Attention mechanism Scene text detection
Online Access:	https://doi.org/10.1007/s40747-025-01987-6